Information Retrieval and Retrieval-Augmented Generation
Abstract
This chapter introduces information retrieval (IR) and retrieval-augmented generation (RAG) as important natural language processing (NLP) tasks for efficiently obtaining relevant information from vast datasets. RAG combines IR with generative capabilities, providing contextually appropriate and factual responses to users’ questions. The chapter explains key concepts such as cosine similarity and embeddings, which facilitate nuanced retrieval processes. The chapter presents a practical Python example implementing a simple IR and RAG system, providing guidance for design decisions such as chunk size, model selection, and query crafting.
Read the paper
Related studies
- Knowledge Management Perspective of Generative Artificial Intelligence
- Navigating Generative Artificial Intelligence Promises and Perils for Knowledge and Creative Work
- Characterizing the evolving research on enterprise content management
- Large language models and multimodal foundation models for precision oncology
- From Generative AI to Extended Reality: Multidisciplinary Perspectives on the Challenges, Opportunities, and Future of Educational Computing
- Generative Artificial Intelligence: A New Engine for Advancing Environmental Science and Engineering
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.